© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 112664
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ım
    -0.27
    mutable
    -0.27
    ä¹ŁæĹłæ³ķ
    -0.26
    å¤įæĿĤçļĦ
    -0.26
     mutable
    -0.26
     complex
    -0.25
    ä¹Łä¸įä¼ļ
    -0.25
    åĿļä¿¡
    -0.25
     Soph
    -0.25
    ites
    -0.24
    POSITIVE LOGITS
    à¹Īà¸Ńà¸ĩ
    0.27
    ilib
    0.25
     AuthService
    0.25
    cq
    0.25
    itat
    0.25
     Resident
    0.25
    æī®
    0.25
    eyes
    0.24
    .av
    0.24
     kernels
    0.24
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.